Metraipolis › archive › dc_eeaa965aab6c

Wide View Synthesis from Overlapping Perspective Cameras in Autonomous Driving — arXiv:2611.07081

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.07081
License (as archived)
CC0-1.0
Archived
2026-11-06T14:53:17.296Z
SHA-256 of the archived text
64b65e3d94631964454185abb90a3eb89e8becf38f23ebb7a24372b9461aeb42
Stable URL of this page
https://metraipolis.com/documento/dc_eeaa965aab6c

How to cite

Wide View Synthesis from Overlapping Perspective Cameras in Autonomous Driving — arXiv:2611.07081 — arXiv (en), https://arxiv.org/abs/2611.07081 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eeaa965aab6c (Metraipolis archive dc_eeaa965aab6c, sha256 64b65e3d94631964454185abb90a3eb89e8becf38f23ebb7a24372b9461aeb42)
BibTeX
@misc{dceeaa965aab6c,
  title = {Wide View Synthesis from Overlapping Perspective Cameras in Autonomous Driving — arXiv:2611.07081},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.07081},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eeaa965aab6c; sha256 64b65e3d94631964454185abb90a3eb89e8becf38f23ebb7a24372b9461aeb42},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07081. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multi-perspective-camera systems are widely adopted since they provide broad visual coverage for autonomous driving, motivating the synthesis of a unified wide view from spatially separated observations. In this work, we formulate wide view synthesis (WVS), which aims to synthesize a geometrically consistent wide view at a specified virtual viewpoint from multiple perspective cameras. Unlike conventional image stitching, WVS requires reasoning about 3D geometry and visibility to handle depth-dependent parallax and occlusions arising from spatially separated camera centers. While vanilla 3D Gaussian Splatting (3DGS) enables high-fidelity view synthesis, its reliance on per-scene optimization limits its applicability to driving scenes. Furthermore, WVS introduces additional challenges, *e.g.*, peripheral stretching under perspective projection and photometric inconsistencies across cameras. To address these challenges, we propose **Wide-View Gaussian Splatting (WV-GS)**, a feed-forward Gaussian-splatting framework that synthesizes wide views without per-scene optimization. Specifically, we introduce Piecewise Perspective Rendering (PPR) to mitigate peripheral stretching through local perspective projections sharing a common camera center, and Spatial Affine Photometric Modeling (SAPM) to account for camera-dependent photometric variations during training. We further introduce **WideDrive**, a synthetic benchmark providing dense ground-truth wide views and adapt a LiDAR-projected sparse-reference protocol to real-world datasets. Extensive experiments on multiple datasets demonstrate the effectiveness of WV-GS for WVS. Dataset and code will be publicly released.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.07081 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-06T14:25:42.604Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).